paper-with-me

Papers

GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting

2026-03-19 · Ahmed Tawfik Aboukhadra, Marcel Rogge, Nadia Robertini, Abdalla Arafa, Jameel Malik, Ahmed Elhayek, Didier Stricker arxiv

Understanding realistic hand-object interactions from monocular RGB videos is essential for AR/VR, robotics, and embodied AI. Existing methods rely on category-specific templates or heavy computation, yet still produce physically inconsistent hand-object alignment in 3D. We introduce GHOST (Gaussian Hand-Object Splatting), a fast, category-agnostic framework for reconstructing dynamic hand-object interactions using 2D Gaussian Splatting. GHOST represents both hands and objects as dense, view-consistent Gaussian discs and introduces three key innovations: (1) a geometric-prior retrieval and consistency loss that completes occluded object regions, (2) a grasp-aware alignment that refines hand translations and object scale to ensure realistic contact, and (3) a hand-aware background loss that prevents penalizing hand-occluded object regions. GHOST achieves complete, physically consistent, and animatable reconstructions from a single RGB video while running an order of magnitude faster than prior category-agnostic methods. Extensive experiments on ARCTIC, HO3D, and in-the-wild datasets demonstrate state-of-the-art accuracy in 3D reconstruction and 2D rendering quality, establishing GHOST as an efficient and robust solution for realistic hand-object interaction modeling. Code is available at https://github.com/ATAboukhadra/GHOST.

📄 PDF Abstract BibTeX arXiv:2603.18912

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

Similar Papers 제목 키워드 기반

Description of the Training Process of Neural Networks via Ergodic Theorem : Ghost nodes

2025-07-01 · Eun-Ji Park, Sangwon Yun arxiv

Recent studies have proposed interpreting the training process from an ergodic perspective. Building on this foundation, we present a unified framework for understanding and accelerating the training of deep neural netwo…

Fast Computational Ghost Imaging using Unpaired Deep Learning and a Constrained Generative Adversarial Network

2021-06-09 · Fatemeh Alishahi, Amirhossein Mohajerin-Ariaei

The unpaired training can be the only option available for fast deep learning-based ghost imaging, where obtaining a high signal-to-noise ratio (SNR) image copy of each low SNR ghost image could be practically time-consu…

Deep LearningGenerative Adversarial Network

HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video

2023-11-30 · CVPR 2024 1 · Zicong Fan, Maria Parelli, Maria Eleni Kadoglou, Muhammed Kocabas 외

Since humans interact with diverse objects every day, the holistic 3D capture of these interactions is important to understand and model human behaviour. However, most existing methods for hand-object reconstruction from…

3D ReconstructionObjectObject Reconstruction

1st Place Solution to the 8th HANDS Workshop Challenge -- ARCTIC Track: 3DGS-based Bimanual Category-agnostic Interaction Reconstruction

2024-09-28 · Jeongwan On, Kyeonghwan Gwak, Gunyoung Kang, Hyein Hwang 외

This report describes our 1st place solution to the 8th HANDS workshop challenge (ARCTIC track) in conjunction with ECCV 2024. In this challenge, we address the task of bimanual category-agnostic hand-object interaction …

3DGSObject

GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction

2026-05-15 · Leyang Chen, Junyi Wu, Zhiteng Li, Yulun Zhang arxiv

Streaming 3D reconstruction from long monocular video sequences requires maintaining a key-value (KV) cache that grows linearly with sequence length, creating a severe memory bottleneck. Existing approaches either trunca…

3D Reconstruction